Hybrid Quantum-Classical Generative Adversarial Networks with Transfer Learning

TL;DR

This paper explores hybrid quantum-classical GAN architectures with transfer learning, demonstrating that integrating Variational Quantum Circuits in both generator and discriminator enhances image quality and training efficiency.

Contribution

It systematically investigates the impact of quantum components in GANs, showing that fully hybrid models outperform classical baselines in image synthesis tasks.

Findings

Fully hybrid models produce higher quality images.

Quantum blocks in the generator accelerate early visual structure emergence.

Incorporating quantum blocks in both networks yields the best overall performance.

Abstract

Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images. However, critical questions remain unanswered regarding how quantum principles might best enhance their representational and computational capacity. In this paper, we investigate hybrid quantum-classical GAN architectures supplemented by transfer learning to systematically examine whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over a fully classical baseline. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, produce images with higher quality and achieve more favorable quantitative metrics compared to their fully classical counterparts. In particular, placing the quantum block in the generator appears to accelerate the early emergence of visual structure, whereas placing it in the discriminator slows early visual convergence but improves the final quantitative quality metric. Incorporating quantum blocks into both networks yields the strongest overall performance. Moreover, the model sustains comparable performance even when the dataset size is reduced. Overall, the results underscore that carefully integrating quantum computing with classical adversarial training and pretrained feature extraction can enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware.